Internet scale reverse traceroute

Abstract

Knowledge of Internet paths allows operators and researchers to better understand the Internet and troubleshoot problems. Paths are often asymmetric, so measuring just the forward path only gives partial visibility. Despite the existence of Reverse Traceroute, a technique that captures reverse paths (the sequence of routers traversed by traffic from an arbitrary, uncontrolled destination to a given source), this technique did not fulfill the needs of operators and the research community, as it had limited coverage, low throughput, and inconsistent accuracy. In this paper we design, implement and evaluate revtr 2.0, an Internet-scale Reverse Traceroute system that combines novel measurement approaches and studies with a large-scale deployment to improve throughput, accuracy, and coverage, enabling the first exploration of reverse paths at Internet scale. revtr 2.0 can run 15M reverse traceroutes in one day. This scale allows us to open the system to external sources and users, and supports tasks such as traffic engineering and troubleshooting. CCS CONCEPTS• Networks → Network measurement; Network monitoring.

Replication: Towards a Publicly Available Internet Scale IP Geolocation Dataset

“…With no assumption on the reverse paths from L to VP and T to VP, we cannot isolate the D1 and D2 terms. If we do the assumption that the last link (R1, L) and (R1, T) is symmetric and then the reverse paths from R1 are the same (which should be the case because of destination based routing [45]), we have now: and so we can compute D1 and D2. The assumption of symmetry between two hops has been shown to be valid in 90% of the cases when the two hops belong to the same AS [45], so we see that further analysis needs to be done when one wants to compute D1 and D2.…”

Poster: Towards a Publicly Available Framework to Process Traceroutes with MetaTrace

“…However, it is important to clarify that we are not asserting ClickHouse as the ultimate solution for processing traceroutes. Nevertheless, based on our experience, ClickHouse has proven to be highly reliable and has fulfilled our requirements for several years [8,12,13]. We believe it is valuable to share this information with the community.…”

The best of both worlds

“…This section investigates the results of Table 1 to understand why many clients route to sites announcing prepended routes, especially when sea1 is the non-prepending (i.e., intended) site but only attracted responses from 6% of targets. To summarize, we use reverse traceroute [41] to measure the routes and find that 82% of targets route to another site rather than sea1 because the other route is preferred according to standard BGP policy (e.g., via a customer rather than a peer). For 54% of targets (including a subset of the 82%), providers prefer to route through an R&E network to another site, rather than through a commercial network to sea1.…”